mercurial/bdiff.c
author Pierre-Yves David <pierre-yves.david@logilab.fr>
Tue, 16 Mar 2010 19:52:56 +0100
changeset 10716 5f92bde72eef
parent 10500 e96597c8d0ea
child 11364 0044193a1c45
permissions -rw-r--r--
check-code: Only call check-code if __name__ = "__main__". This changeset moves the code that actually executes something to the "if __name__ = '__main__'" section to allow the file to be imported as a module.
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     1
/*
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     2
 bdiff.c - efficient binary diff extension for Mercurial
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     3
2859
345bac2bc4ec update copyrights.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2600
diff changeset
     4
 Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     5
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     6
 This software may be used and distributed according to the terms of
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     7
 the GNU General Public License, incorporated herein by reference.
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     8
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     9
 Based roughly on Python difflib
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    10
*/
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    11
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    12
#include <Python.h>
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    13
#include <stdlib.h>
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    14
#include <string.h>
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
    15
#include <limits.h>
867
0cd2ee61b10a Allow Mercurial to build on HP-UX 11
tksoh@users.sourceforge.net
parents: 839
diff changeset
    16
3561
8c617d48564a add AIX to the list of compilers that don't have inline keyword
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 3369
diff changeset
    17
#if defined __hpux || defined __SUNPRO_C || defined _AIX
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
    18
#define inline
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2577
diff changeset
    19
#endif
1759
5afd459db177 Sunpro compiler patch
Fabian Otto <sigsegv@alchiba.ni.cs.tu-berlin.de>
parents: 1542
diff changeset
    20
8858
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
    21
#ifdef __linux
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
    22
#define inline __inline
8858
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
    23
#endif
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
    24
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    25
#ifdef _WIN32
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
    26
#ifdef _MSC_VER
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
    27
#define inline __inline
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
    28
typedef unsigned long uint32_t;
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
    29
#else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
    30
#include <stdint.h>
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
    31
#endif
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    32
static uint32_t htonl(uint32_t x)
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    33
{
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    34
	return ((x & 0x000000ffUL) << 24) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    35
		((x & 0x0000ff00UL) <<  8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    36
		((x & 0x00ff0000UL) >>  8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    37
		((x & 0xff000000UL) >> 24);
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    38
}
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    39
#else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
    40
#include <sys/types.h>
7036
bfad9865b1dc allow Mercurial to compile on Haiku
Scott McCreary <scottmc2@gmail.com>
parents: 5620
diff changeset
    41
#if defined __BEOS__ && !defined __HAIKU__
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
    42
#include <ByteOrder.h>
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
    43
#else
597
e530637ea060 [PATCH] use <arpa/inet.h> instead of <netinet/in.h> for ntohl/htonl
mpm@selenic.com
parents: 553
diff changeset
    44
#include <arpa/inet.h>
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
    45
#endif
2543
860e9c83fc59 Include inttypes.h instead of stdint.h (fixes issue299)
Thomas Arendsen Hein <thomas@intevation.de>
parents: 2483
diff changeset
    46
#include <inttypes.h>
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    47
#endif
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    48
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    49
struct line {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
    50
	int h, len, n, e;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    51
	const char *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    52
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    53
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
    54
struct pos {
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
    55
	int pos, len;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
    56
};
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
    57
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    58
struct hunk {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    59
	int a1, a2, b1, b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    60
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    61
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    62
struct hunklist {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    63
	struct hunk *base, *head;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    64
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    65
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    66
int splitlines(const char *a, int len, struct line **lr)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    67
{
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
    68
	int h, i;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    69
	const char *p, *b = a;
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
    70
	const char * const plast = a + len - 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    71
	struct line *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    72
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    73
	/* count the lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    74
	i = 1; /* extra line for sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    75
	for (p = a; p < a + len; p++)
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
    76
		if (*p == '\n' || p == plast)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    77
			i++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    78
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
    79
	*lr = l = (struct line *)malloc(sizeof(struct line) * i);
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    80
	if (!l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    81
		return -1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    82
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    83
	/* build the line array and calculate hashes */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    84
	h = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    85
	for (p = a; p < a + len; p++) {
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
    86
		/* Leonid Yuriev's hash */
7187
a79d3f535809 spaces->tabs in one line of a C extension for consistency
Thomas Arendsen Hein <thomas@intevation.de>
parents: 7036
diff changeset
    87
		h = (h * 1664525) + *p + 1013904223;
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
    88
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
    89
		if (*p == '\n' || p == plast) {
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
    90
			l->h = h;
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
    91
			h = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    92
			l->len = p - b + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    93
			l->l = b;
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
    94
			l->n = INT_MAX;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    95
			l++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    96
			b = p + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    97
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    98
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    99
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   100
	/* set up a sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   101
	l->h = l->len = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   102
	l->l = a + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   103
	return i - 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   104
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   105
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   106
int inline cmp(struct line *a, struct line *b)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   107
{
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   108
	return a->h != b->h || a->len != b->len || memcmp(a->l, b->l, a->len);
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   109
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   110
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   111
static int equatelines(struct line *a, int an, struct line *b, int bn)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   112
{
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   113
	int i, j, buckets = 1, t, scale;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   114
	struct pos *h = NULL;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   115
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   116
	/* build a hash table of the next highest power of 2 */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   117
	while (buckets < bn + 1)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   118
		buckets *= 2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   119
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
   120
	/* try to allocate a large hash table to avoid collisions */
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   121
	for (scale = 4; scale; scale /= 2) {
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
   122
		h = (struct pos *)malloc(scale * buckets * sizeof(struct pos));
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   123
		if (h)
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   124
			break;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
   125
	}
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
   126
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   127
	if (!h)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   128
		return 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   129
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
   130
	buckets = buckets * scale - 1;
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
   131
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   132
	/* clear the hash table */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   133
	for (i = 0; i <= buckets; i++) {
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   134
		h[i].pos = INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   135
		h[i].len = 0;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   136
	}
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   137
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   138
	/* add lines to the hash table chains */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   139
	for (i = bn - 1; i >= 0; i--) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   140
		/* find the equivalence class */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   141
		for (j = b[i].h & buckets; h[j].pos != INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   142
		     j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   143
			if (!cmp(b + i, b + h[j].pos))
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   144
				break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   145
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   146
		/* add to the head of the equivalence class */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   147
		b[i].n = h[j].pos;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   148
		b[i].e = j;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   149
		h[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   150
		h[j].len++; /* keep track of popularity */
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   151
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   152
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   153
	/* compute popularity threshold */
9534
8e202431d620 bdiff: gradually enable the popularity hack
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 8858
diff changeset
   154
	t = (bn >= 31000) ? bn / 1000 : 1000000 / (bn + 1);
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   155
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   156
	/* match items in a to their equivalence class in b */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   157
	for (i = 0; i < an; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   158
		/* find the equivalence class */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   159
		for (j = a[i].h & buckets; h[j].pos != INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   160
		     j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   161
			if (!cmp(a + i, b + h[j].pos))
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   162
				break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   163
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   164
		a[i].e = j; /* use equivalence class for quick compare */
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
   165
		if (h[j].len <= t)
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   166
			a[i].n = h[j].pos; /* point to head of match list */
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   167
		else
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   168
			a[i].n = INT_MAX; /* too popular */
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   169
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   170
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   171
	/* discard hash tables */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   172
	free(h);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   173
	return 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   174
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   175
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   176
static int longest_match(struct line *a, struct line *b, struct pos *pos,
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   177
			 int a1, int a2, int b1, int b2, int *omi, int *omj)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   178
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   179
	int mi = a1, mj = b1, mk = 0, mb = 0, i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   180
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   181
	for (i = a1; i < a2; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   182
		/* skip things before the current block */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   183
		for (j = a[i].n; j < b1; j = b[j].n)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   184
			;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   185
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   186
		/* loop through all lines match a[i] in b */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   187
		for (; j < b2; j = b[j].n) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   188
			/* does this extend an earlier match? */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   189
			if (i > a1 && j > b1 && pos[j - 1].pos == i - 1)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   190
				k = pos[j - 1].len + 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   191
			else
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   192
				k = 1;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   193
			pos[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   194
			pos[j].len = k;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   195
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   196
			/* best match so far? */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   197
			if (k > mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   198
				mi = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   199
				mj = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   200
				mk = k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   201
			}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   202
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   203
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   204
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   205
	if (mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   206
		mi = mi - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   207
		mj = mj - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   208
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   209
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   210
	/* expand match to include neighboring popular lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   211
	while (mi - mb > a1 && mj - mb > b1 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   212
	       a[mi - mb - 1].e == b[mj - mb - 1].e)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   213
		mb++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   214
	while (mi + mk < a2 && mj + mk < b2 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   215
	       a[mi + mk].e == b[mj + mk].e)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   216
		mk++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   217
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   218
	*omi = mi - mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   219
	*omj = mj - mb;
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
   220
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   221
	return mk + mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   222
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   223
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   224
static void recurse(struct line *a, struct line *b, struct pos *pos,
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   225
		    int a1, int a2, int b1, int b2, struct hunklist *l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   226
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   227
	int i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   228
10500
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   229
	while (1) {
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   230
		/* find the longest match in this chunk */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   231
		k = longest_match(a, b, pos, a1, a2, b1, b2, &i, &j);
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   232
		if (!k)
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   233
			return;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   234
10500
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   235
		/* and recurse on the remaining chunks on either side */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   236
		recurse(a, b, pos, a1, i, b1, j, l);
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   237
		l->head->a1 = i;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   238
		l->head->a2 = i + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   239
		l->head->b1 = j;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   240
		l->head->b2 = j + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   241
		l->head++;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   242
		/* tail-recursion didn't happen, so doing equivalent iteration */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   243
		a1 = i + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   244
		b1 = j + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
   245
	}
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   246
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   247
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   248
static struct hunklist diff(struct line *a, int an, struct line *b, int bn)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   249
{
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   250
	struct hunklist l;
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   251
	struct hunk *curr;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   252
	struct pos *pos;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   253
	int t;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   254
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   255
	/* allocate and fill arrays */
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   256
	t = equatelines(a, an, b, bn);
5571
f84bb2e1cc3a fix calloc(0, ...) issue
Jim Hague <jim.hague@acm.org>
parents: 5452
diff changeset
   257
	pos = (struct pos *)calloc(bn ? bn : 1, sizeof(struct pos));
827
a61728b58dc0 Fix array overflow bug in bdiff
"Wallace, Eric S" <eric.s.wallace@intel.com>
parents: 597
diff changeset
   258
	/* we can't have more matches than lines in the shorter file */
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
   259
	l.head = l.base = (struct hunk *)malloc(sizeof(struct hunk) *
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
   260
	                                        ((an<bn ? an:bn) + 1));
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   261
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   262
	if (pos && l.base && t) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   263
		/* generate the matching block list */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   264
		recurse(a, b, pos, 0, an, 0, bn, &l);
4131
1ca664c964e0 don't return uninitialized memory from bdiff.blocks()
Erling Ellingsen <erlingalf@gmail.com>
parents: 3561
diff changeset
   265
		l.head->a1 = l.head->a2 = an;
1ca664c964e0 don't return uninitialized memory from bdiff.blocks()
Erling Ellingsen <erlingalf@gmail.com>
parents: 3561
diff changeset
   266
		l.head->b1 = l.head->b2 = bn;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   267
		l.head++;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   268
	}
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   269
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
   270
	free(pos);
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   271
7625
930a2be7e875 bdiff: add comment about normalization
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7189
diff changeset
   272
	/* normalize the hunk list, try to push each hunk towards the end */
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   273
	for (curr = l.base; curr != l.head; curr++) {
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   274
		struct hunk *next = curr + 1;
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   275
		int shift = 0;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   276
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   277
		if (next == l.head)
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   278
			break;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   279
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   280
		if (curr->a2 == next->a1)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   281
			while (curr->a2 + shift < an && curr->b2 + shift < bn
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   282
			       && !cmp(a + curr->a2 + shift,
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   283
				       b + curr->b2 + shift))
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   284
				shift++;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   285
		else if (curr->b2 == next->b1)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   286
			while (curr->b2 + shift < bn && curr->a2 + shift < an
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   287
			       && !cmp(b + curr->b2 + shift,
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
   288
				       a + curr->a2 + shift))
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   289
				shift++;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   290
		if (!shift)
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   291
			continue;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   292
		curr->b2 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   293
		next->b1 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   294
		curr->a2 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   295
		next->a1 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   296
	}
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
   297
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   298
	return l;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   299
}
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   300
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   301
static PyObject *blocks(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   302
{
435
e731d25ddab2 Fix a compile warning for bdiff
mpm@selenic.com
parents: 433
diff changeset
   303
	PyObject *sa, *sb, *rl = NULL, *m;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   304
	struct line *a, *b;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
   305
	struct hunklist l = {NULL, NULL};
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   306
	struct hunk *h;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   307
	int an, bn, pos = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   308
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   309
	if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   310
		return NULL;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   311
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   312
	an = splitlines(PyString_AsString(sa), PyString_Size(sa), &a);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   313
	bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &b);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   314
	if (!a || !b)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   315
		goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   316
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   317
	l = diff(a, an, b, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   318
	rl = PyList_New(l.head - l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   319
	if (!l.head || !rl)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   320
		goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   321
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
   322
	for (h = l.base; h != l.head; h++) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   323
		m = Py_BuildValue("iiii", h->a1, h->a2, h->b1, h->b2);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   324
		PyList_SetItem(rl, pos, m);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   325
		pos++;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   326
	}
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   327
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   328
nomem:
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   329
	free(a);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   330
	free(b);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   331
	free(l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   332
	return rl ? rl : PyErr_NoMemory();
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   333
}
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   334
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   335
static PyObject *bdiff(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   336
{
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   337
	char *sa, *sb;
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   338
	PyObject *result = NULL;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   339
	struct line *al, *bl;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
   340
	struct hunklist l = {NULL, NULL};
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   341
	struct hunk *h;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   342
	char encode[12], *rb;
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   343
	int an, bn, len = 0, la, lb;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   344
3369
4bad632913d8 python2.5 PyArg_ParseTuple fix
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 3335
diff changeset
   345
	if (!PyArg_ParseTuple(args, "s#s#:bdiff", &sa, &la, &sb, &lb))
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   346
		return NULL;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   347
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   348
	an = splitlines(sa, la, &al);
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   349
	bn = splitlines(sb, lb, &bl);
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   350
	if (!al || !bl)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   351
		goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   352
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   353
	l = diff(al, an, bl, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   354
	if (!l.head)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   355
		goto nomem;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   356
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   357
	/* calculate length of output */
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
   358
	la = lb = 0;
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
   359
	for (h = l.base; h != l.head; h++) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   360
		if (h->a1 != la || h->b1 != lb)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   361
			len += 12 + bl[h->b1].l - bl[lb].l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   362
		la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   363
		lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   364
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   365
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   366
	result = PyString_FromStringAndSize(NULL, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   367
	if (!result)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   368
		goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   369
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   370
	/* build binary patch */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   371
	rb = PyString_AsString(result);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   372
	la = lb = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   373
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
   374
	for (h = l.base; h != l.head; h++) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   375
		if (h->a1 != la || h->b1 != lb) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   376
			len = bl[h->b1].l - bl[lb].l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   377
			*(uint32_t *)(encode)     = htonl(al[la].l - al->l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   378
			*(uint32_t *)(encode + 4) = htonl(al[h->a1].l - al->l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   379
			*(uint32_t *)(encode + 8) = htonl(len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   380
			memcpy(rb, encode, 12);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   381
			memcpy(rb + 12, bl[lb].l, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   382
			rb += 12 + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   383
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   384
		la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   385
		lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   386
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   387
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   388
nomem:
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   389
	free(al);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   390
	free(bl);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   391
	free(l.base);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   392
	return result ? result : PyErr_NoMemory();
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   393
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   394
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   395
static char mdiff_doc[] = "Efficient binary diff.";
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   396
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   397
static PyMethodDef methods[] = {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   398
	{"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
   399
	{"blocks", blocks, METH_VARARGS, "find a list of matching lines\n"},
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   400
	{NULL, NULL}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   401
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   402
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   403
PyMODINIT_FUNC initbdiff(void)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   404
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   405
	Py_InitModule3("bdiff", methods, mdiff_doc);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   406
}
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
   407